Response to Amendment
Claims 1-3, 5-10, 12-17 and 19-20 are pending.
Claims 1-3, 5-10, 12-17 and 19-20 are rejected.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-3, 5-10, 12-17 and 19-2 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.Claim 1 states the limitation “wherein each input-interval set contains … and the location information of the user”. Although, the specification (paragraphs 0041, 0447-0048) supports the teaching of the location of the user, these paragraphs do not teach the the location information of the user is contained in each input-interval set. Paragraph 0052 seems to teach that each input-interval set include location information. However, the location information in paragraph 0052 seems to refer to touch input location (location in the screen) but not the location of the user.
Claims 2-3, 5-7 depends on claim 1 and are therefore rejected under the same rationale.
Claims 8-10, 12-17 and 19-20 has similar language and re therefore rejected under the same rationale.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 5-6, 8-10, 12-13, 15-17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Arroyo-Gallego et al (Pub. No.: US 2021/0236044 A1) in view of Wisgo (Pub. No.: US 2023/0111812 A1), Gaincardo et al (Pub. No.: US 2015/0272504 A1) and CAVALLARO CORTI et al (Pub. No.: US 2024/0179163 A1).
As per claim 1, Arroyo-Gallego discloses a computer-implemented method, the method comprising: - tracking user inputs, wherein the user inputs comprise touch inputs (Arroyo-Gallego, paragraph 0029-0030, 0033-0034, 0270, wherein keystrokes of a user are analyzed in order to assess a health condition or functional state of the user. In some cases, the keystrokes occur while a user is typing on a keyboard (e.g., a mechanical keyboard). During the typing, keys of the keyboard may physically move relative to another portion of the keyboard. In some cases, the keystrokes occur when a user is typing on a touchscreen.In some use cases of this invention, keystroke data is unobtrusively gathered while a user types in a natural and free manner during the user's ordinary daily activities. Data collection software may unobtrusively collect the typing information while the user types); - tracking time intervals between the user inputs (Arroyo-Gallego, paragraph 0040-0041, 0058-0059, wherein augmented keystroke data may include, for each keystroke: (a) time of key press; and (b) time of key release. The enriched keystroke data may include hold time of each keystroke. The hold time of a keystroke may be the amount of time that elapses between the press time and release time of the keystroke. In other words, the hold time of a keystroke may be equal to the difference between the release time of the keystroke and the press time of the keystroke. The enriched keystroke data may also include flight time for each pair of consecutive keystrokes. For each pair of consecutive keystrokes, the flight time may be the amount of time that elapses between the press times of the two keystrokes in the pair. In other words, for each pair of consecutive keystrokes, the flight time may be equal to the difference between press time of the second keystroke in the pair and press time of the first keystroke in the pair. More generally, flight time may be calculated as the temporal interval between corresponding points in time in two consecutive keystrokes (e.g., between press times of the two consecutive keystrokes, or between release times of the two consecutive keystrokes, or between times in the temporal middle of the two consecutive keystrokes)); - storing input-interval sets, wherein each input-interval set containing at least one touch input from the tracked user inputs and at least one time interval from the tracked time intervals between the user inputs, wherein the at least one touch input corresponds to the at least one time interval (Arroyo-Gallego, paragraph 0040-0041, 0153, 0270, wherein augmented keystroke data may include, for each keystroke: (a) time of key press; and (b) time of key release. In some cases: (a) a set of data regarding typing by a user is fed as input into one or more ML algorithms; (b) the inputted set of data includes augmented keystroke data, enriched keystroke data, augmented keystroke tensors, enriched keystroke data, and/or features (e.g., features described in the section above titled “Features”). More specifically, for each keystroke the program may store the timestamps corresponding to the press and release events); - pretraining a foundation model based on the stored input-interval sets (Arroyo-Gallego, Fig 10, paragraph 0140, 0155, 0164 0266-0067 wherein In FIG. 10, four machine learning (ML) models 1006 are employed. Each ML model receives a different type of input 1001. In FIG. 10: (a) a first ML model receives, as input, data that represents or is derived from measurements of keystrokes typed on a keyboard by a user during a natural typing session; (b) a second ML model receives, as input, data that represents or is derived from measurements of keystrokes typed on a touchscreen by a user during a natural typing session; (c) a third ML model receives, as input, data that represents or is derived from measurements of keystrokes typed on a keyboard by a user during a controlled typing session; and (d) a fourth ML model receives, as input, data that represents or is derived from measurements of keystrokes typed on a touchscreen by a user during a controlled typing session); and- training the foundation model for a particular task (Arroyo-Gallego, Fig 10, paragraph 0127, 0265-0267, wherein In some implementations, location-based keystroke tensors (or location-based keystroke distributions) are used as the input to a machine learning model that has been trained to evaluate whether one or more patterns of keystrokes deviate from normal. For instance, the machine learning model may be trained to evaluate patterns of bimanual motor degradation, abnormal asymmetrical performance and irregular patterns in multi-finger synergies. Training of the machine learning model may be based on a definition of what is expected as a healthy pattern versus diseased pattern). Arroyo-Gallego does not explicitly disclose: - associating the tracked user inputs with location information of a user;- each input-interval set contains the location information of the user. However, Wisgo discloses - associating the tracked user inputs with location information of a user (Wisgo, Fig 12, paragraph 0118, wherein “At a step 1212 of the routine 1200, the context determination engine 514 may determine a current location of the client device 202. The location of the client device 202 may be determined, for example, using a global positioning system (GPS) component, one or more networks to which the client device 202 is connected, one or more wireless networks signals detected by the client device 202, etc. Users may exhibit slightly different typing behavior when operating a client device 202 at different locations (e.g., in the office versus at home), and context data that is indicative of such locations may be helpful in selecting the most appropriate keystroke behavior data to compare with the keystroke timing data being measured by the keystroke monitoring engine 508”);- each input-interval set contains the location information of the user (Wisgo, Fig 1D, 10, paragraph 0037, 0107, wherein “In any event, at a step 1116, the keystroke evaluation engine 512 may compare the keystroke timing data (received from the authentication UI engine 506 per the decision step 1102) with retrieved and/or accessible keystroke behavior of one or more individuals (e.g., as stored in one or more tables 1000—shown in FIG. 10) to assess whether the keystroke timing data is sufficiently similar to the keystroke behavior data of any one individual to warrant a determination that the person whose keystrokes generated the new keystroke timing data is likely the same person whose prior keystrokes resulted in the generation of the keystroke behavior data. As noted above, in some implementations, the context data received from authentication UI engine 506 may be used to identify a particular subset of the keystroke behavior data for one or more users that is to be used for the comparison performed at the step 1106. For instance, if the received context data indicates that the received keystroke timing data was acquired in a certain contextual circumstance, e.g., by a particular keyboard 108 and/or client device 202, or where the character-to-character transitions occurred within a particular word, the keystroke evaluation engine 512 may use only the stored keystroke behavior data associated with that same context for such a comparison. The “context” entries 1002 in the table 1000 (which may correspond to the “context” entries 118 in the tables 114—shown in FIG. 1D) may, for example, be used to select the keystroke behavior data that is associated with a particular contextual circumstance”).
Therefore, it would have it would have been obvious to one ordinary skill in the art before the effective filing date of the invention to incorporate Wisgo teachings into Arroyo-Gallego to achieve the claimed limitations because this would have provided an improved mechanism for identifying users based on keystroke behavior by factoring context data such as user location since users may exhibit slightly different typing behavior when operating a client device at different locations (e.g., in the office versus at home), and context data that is indicative of such locations may be helpful in selecting the most appropriate keystroke behavior data (see Wisgo paragraph 0118). Arroyo-Gallego disclosed that the user inputs comprise hold time which represent the time for the user’s finger to exert pressure on the key until the user’s finger releasees pressure from the key (see Arroyo-Gallego paragraph 0031). The hold time can be used to represent the respective pressure used for each touch input as claimed. However, to make the record clear and assuming that the claimed pressure is not represented by time, the examiner introduces Gaincardo to disclose that the user inputs comprise a respective pressure used for each touch input set also contains the pressure (Gaincardo, paragraph 0054, 0061, Measurements performed by one or more sensors of the electronic device may provide additional information that may be complementary to the information acquired through analysis of keystroke events. A sensor may measure motion, orientation, position, typing pressure, and/or various environmental conditions. A sensor may be an accelerometer, gravity sensor, gyroscope, rotational vector sensor, orientation sensor, a magnetometer, pressure sensor, thermometer, barometer, microphone, and/or photometer. A diagnostic tool may analyze data from one or more sensors (e.g. accelerometer data, gyroscope data, typing pressure data, location data, voice data). In some embodiments, the analysis performed by the diagnostic tool may include analyzing information from one or more sensors that is associated with keystroke events related to a user input. As an example, pressure sensors as part of a touchscreen may measure pressure as a user touches a location of the touchscreen such as a virtual key. The one or more sensors may provide information related to the user's movement, location, orientation, voice, and/or typing pressure. Module 112 may occasionally, periodically, or continuously (e.g., as the information is received) transmit information from the one or more sensors to system 114.).
Therefore, it would have it would have been obvious to one ordinary skill in the art before the effective filing date of the invention to incorporate Gaincardo teachings into Arroyo-Gallego and Wisgo to achieve the claimed limitations because this would have provided an improved mechanism for evaluating that person's motor function and aiding in the diagnosis of neurological impairments. Such a diagnostic tool may evaluate a motor function of a person through analyzing a sequence of keystroke events indicating keyboard keys, such as physical or touchscreen keyboard keys, that the person has pressed over a period of time (see Gaincardo paragraph 0043). In addition, Arroyo-Gallego particular task is identifying or predicting a disease (Arroyo-Gallego, paragraph 0129-0132, 0165, wherein the machine learning algorithm(s) may assess the presence, severity or probability of, or a change in, one or more diseases, such as: Alzheimer's disease; mild cognitive impairment; dementia with Lewy bodies, Parkinson's disease; multiple sclerosis; frontotemporal degeneration; Huntington's disease; Lewy body disease; prion disease; HIV/AIDS; carpal tunnel syndrome; osteoarthritis; psoriatic arthritis; rheumatoid arthritis; peripheral nerve disorders (e.g., Charcot-Marie-Tooth disease, chronic inflammatory demyelinating polyneuropathy, or amyloidosis), spine disease (such as spondylosis or myelopathies); and/or brain diseases (such as amyotrophic lateral sclerosis, frontotemporal dementia, other motor-neuron disease, stroke, and dystonia)). However, the same result/procedure/task can discern whether the user is human or non-human. To make the record clear, the examiner interduces Tenaglia to disclose wherein the particular task is discerning whether the user is a human (CAVALLARO CORTI, paragraph 0010, wherein “Data science methods can play a fundamental role in this direction. For instance, time series analysis of keystrokes can help to rule out typing patterns or speeds that are unfeasible for a human operator or a given keyboard layout”; Paragraph 0051-0052, wherein “Therefore, the communication features extracted are derived from the analyzed data packets and then sent to a classification system whose goal is to distinguish between patterns, i.e. USB traffic, generated by a normal human working on a machine or by a malicious traffic injection”, “As stated above, each classifier in this ensemble, given the extracted communication features, either votes for “normal pattern” (human) or “anomalous pattern” (malicious)”).
Therefore, it would have it would have been obvious to one ordinary skill in the art before the effective filing date of the invention to incorporate CAVALLARO CORTI teachings into Arroyo-Gallego, Wisgo and Gaincardo to achieve the claimed limitations because this would have provided a way to improve the security of the system by identifying human users from machine algorithms trying to imitate human actions.
As per claim 2, claim 1 is incorporated and Arroyo-Gallego further discloses wherein the user inputs are characters in an input stream (Arroyo-Gallego, paragraph 0029-0030, 0033-0034, 0270, wherein keystrokes of a user are analyzed in order to assess a health condition or functional state of the user. In some cases, the keystrokes occur while a user is typing on a keyboard (e.g., a mechanical keyboard). During the typing, keys of the keyboard may physically move relative to another portion of the keyboard. In some cases, the keystrokes occur when a user is typing on a touchscreen.In some use cases of this invention, keystroke data is unobtrusively gathered while a user types in a natural and free manner during the user's ordinary daily activities. Data collection software may unobtrusively collect the typing information while the user types);
As per claim 3, claim 1 is incorporated and Arroyo-Gallego further discloses wherein the time intervals are tracked on a scale of milliseconds (Arroyo-Gallego, paragraph 0270, wherein in some cases, the temporal resolution of the data collection software is 3/0.28 (mean/std) milliseconds);
As per claim 5, claim 1 is incorporated and Arroyo-Gallego further discloses wherein tracking user inputs includes tracking user inputs from two or more devices (Arroyo-Gallego, Fig 10, paragraph 0164, 0166, wherein in FIG. 11, multiple users may type on touchscreens (e.g., 1004, 1005, 1006) of mobile computing devices (MCDs) (e.g., 1001, 1002, 1003). Data representing measurements of keystrokes that occur during this typing may be processed by computers (e.g., 1111, 1113, 1115) onboard the respective MCDs. For instance, these onboard computers may comprise microprocessors or microcontrollers. These onboard computers (e.g., 1111, 1113, 1115) may output data that is derived from (and/or represents) the measurements of keystrokes. This data (which is outputted by computers onboard the MCDs) may comprise: (a) enriched keystroke data; (b) augmented keystroke data; (c) data that encodes one or more enriched keystroke tensors; and/or (d) data that encodes one or more augmented keystroke tensors);
As per claim 6, claim 1 is incorporated and Arroyo-Gallego further discloses training a second foundation model, based on the stored input-interval sets, to perform a second task, wherein the second task is identifying or predicting a disease, disorder, or injury (Arroyo-Gallego, paragraph 0129-0132, 0165, wherein the machine learning algorithm(s) may assess the presence, severity or probability of, or a change in, one or more diseases, such as: Alzheimer's disease; mild cognitive impairment; dementia with Lewy bodies, Parkinson's disease; multiple sclerosis; frontotemporal degeneration; Huntington's disease; Lewy body disease; prion disease; HIV/AIDS; carpal tunnel syndrome; osteoarthritis; psoriatic arthritis; rheumatoid arthritis; peripheral nerve disorders (e.g., Charcot-Marie-Tooth disease, chronic inflammatory demyelinating polyneuropathy, or amyloidosis), spine disease (such as spondylosis or myelopathies); and/or brain diseases (such as amyotrophic lateral sclerosis, frontotemporal dementia, other motor-neuron disease, stroke, and dystonia) . FIG. 11 is a block diagram of hardware for a system that assesses a health condition based on keystroke data, in an illustrative implementation of this invention);
Claims 8-10, 12-13, 15-17 and 19-20 are rejected under the same rationale as claims 1-3 and 5-6.
Claims 7 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Arroyo-Gallego et al (Pub. No.: US 2021/0236044 A1) in view of Wisgo (Pub. No.: US 2023/0111812 A1), Gaincardo et al (Pub. No.: US 2015/0272504 A1), CAVALLARO CORTI et al (Pub. No.: US 2024/0179163 A1) and Nath (Pub. No.: US 2023/0093336 A1).
As per claim 7, claim 6 is incorporated and Arroyo-Gallego further discloses performing the particular task (Arroyo-Gallego, paragraph 0129-0132, 0165, wherein the machine learning algorithm(s) may assess the presence, severity or probability of, or a change in, one or more diseases, such as: Alzheimer's disease; mild cognitive impairment; dementia with Lewy bodies, Parkinson's disease; multiple sclerosis; frontotemporal degeneration; Huntington's disease; Lewy body disease; prion disease; HIV/AIDS; carpal tunnel syndrome; osteoarthritis; psoriatic arthritis; rheumatoid arthritis; peripheral nerve disorders (e.g., Charcot-Marie-Tooth disease, chronic inflammatory demyelinating polyneuropathy, or amyloidosis), spine disease (such as spondylosis or myelopathies); and/or brain diseases (such as amyotrophic lateral sclerosis, frontotemporal dementia, other motor-neuron disease, stroke, and dystonia) . FIG. 11 is a block diagram of hardware for a system that assesses a health condition based on keystroke data, in an illustrative implementation of this invention). Arroyo-Gallego. Wisgo, Gaincardo and CAVALLARO CORTI do not explicitly disclose using feedback collected about the performance of the particular task in order to further pretrain or further train the foundation model. However, using feedback to retrain ML model is well known in the art. For example, Nath discloses using feedback collected about the performance of the particular task in order to further pretrain or further train the foundation model (Nath, paragraph 0107, wherein he training engine may train, periodically retrain, and/or iteratively train the machine learning model 148 using feedback provided by a user or generated by the computing device 108).
Therefore, it would have it would have been obvious to one ordinary skill in the art before the effective filing date of the invention to incorporate Nath teachings into Arroyo-Gallego, Wisgo, Gaincardo and CAVALLARO CORTI to achieve the claimed limitations because this would have provided a way to improve the accuracy of the prediction which increase user satisfaction.
Claim 14 is rejected under the same rationale as claim 7.
Note: with respect to the limitation “one or more computer-readable tangible storage media”, the examiner understands the limitation not to include any form of transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide, light pulses passing through a fiber optic cable, electrical signals communicated through a wire, and/or other transmission media (see specification 0023).
Response to Arguments
Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAMZA N ALGIBHAH whose telephone number is (571)270-7212. The examiner can normally be reached 7:30 am - 3:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Wing Chan can be reached at (571) 272-7493. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/HAMZA N ALGIBHAH/Primary Examiner, Art Unit 2441
Prosecution Insights